A Survey on Security Threats and Defensive Techniques of Machine Learning: A Data Driven View

By Qiang Liu, Pan Li, Wentao Zhao, Wei Cai, Shui Yu, Victor C. M. Leung. IEEE Access, 2018

390 citations recorded by the source corpus.

Machine learning is one of the most prevailing techniques in computer science, and it has been widely applied in image processing, natural language processing, pattern recognition, cybersecurity, and other fields. Regardless of successful applications of machine learning algorithms in many scenarios, e.g., facial recognition, malware detection, automatic driving, and intrusion detection, these algorithms and corresponding training data are vulnerable to a variety of security threats, inducing a significant performance decrease. Hence, it is vital to call for further attention regarding security threats and corresponding defensive techniques of machine learning, which motivates a comprehensive survey in this paper. Until now, researchers from academia and industry have found out many security threats against a variety of learning algorithms, including naive Bayes, logistic regression, decision tree, support vector machine (SVM), principle component analysis, clustering, and prevailing deep neural networks. Thus, we revisit existing security threats and give a systematic survey on them from two aspects, the training phase and the testing/inferring phase. After that, we categorize current defensive techniques of machine learning into four groups: security assessment mechanisms, countermeasures in the training phase, those in the testing or inferring phase, data security, and privacy. Finally, we provide five notable trends in the research on security threats and defensive techniques of machine learning, which are worth doing in-depth studies in future.

Subfields: Artificial Intelligence, Computer Networks and Communications, Signal Processing

View Paper: https://www.semanticscholar.org/paper/4a8c332b09bb99333a8bce6a4640a20c1352aa63

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Networks and Communications

In Signal Processing

Citations in the corpus

Adversarial Examples on Object Recognition (2020, background): “Some examples of perturbations are also illustrated in Figure 2a.”
Unleashing the Power of Edge-Cloud Generative AI in Mobile Networks: A Survey of AIGC Services (2023, neutral): “Mobile AIGC networks leverage a collaborative computing framework on the cloud side to provide AIGC services, utilizing a large amount of heterogeneous data and computing power [262], [263], [264], [265].”
LIRA: Learnable, Imperceptible and Robust Backdoor Attacks (2021, background): “However, along with the evolution, recent works have shown DNN models are vulnerable to various categories of adversarial attacks [37, 46, 29], which might be attributed to the lack of model transparency and explainability.”
Adversarial Attacks on Deep Learning Models in Natural Language Processing: A Survey (2019, background): “ering non-deep leaning algorithms to recent deep learning algorithms. It is also from the security point of view to provide detailed analysis on the effect of the attacks and defenses. The authors of [81] reviewed the same problem in a data-driven perspective. They analyzed the attacks and defenses ”
Attacks on Machine Learning: Lurking Danger for Accountability (2019, background): “[42] also discuss different attacks and propose interesting points to consider in future research.”
A Survey of Black-Box Adversarial Attacks on Computer Vision Models (2019, background): “Additional Key Words and Phrases: Deep Neural Networks, Deep Learning, Adversarial Examples, Computer Vision ACM Reference Format: Siddhant Bhambri, Sumanyu Muku, Avinash Tulasi, and Arun Balaji Buduru.”
A Survey of Machine and Deep Learning Methods for Internet of Things (IoT) Security (2018, background): “avoids detection, thereby reducing the performance of the system remarkably [281].”
When Machine Learning Meets Privacy (2020, background): “ing unstructured data, such as text, image, and video. In this context, a systematic study of privacy and ML is essential for future research efforts. Although there are several surveys on this topic [1, 64, 85, 177], The focus has been on a certain type of ML model or specific methods. This study a”
The relationship between trust in AI and trustworthy machine learning technologies (2019, background): “ and possibly repairing tampered data [14, 12, 58]. These methods deal only with data, but it is also relevant to consider integrity during the execution of the algorithm, e.g., in the training stage [26, 13, 11, 61, 85]. 6 Conclusion This paper established the connection between trust as a notion w”
Machine Learning for 5G/B5G Mobile and Wireless Communications: Potential, Limitations, and Future Directions (2019, background): “computer security, intrusion detection, and cyber-physical attacks on mobile and wireless communications [186].”
Application of Big Data and Machine Learning in Smart Grid, and Associated Security Concerns: A Review (2019, background): “Security threats to machine learning techniques specifically can be found in [187].”